Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent
In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical framework to study Continual Learning algorithms in the Neural Tangent Kernel regime. This framework comprises closed form expression of the model through tasks and proxies for Transfer Learning, generalisation and tasks similarity. In this framework, we prove that OGD is robust to Catastrophic Forgetting then derive the first generalisation bound for SGD and OGD for Continual Learning. Finally, we study the limits of this framework in practice for OGD and highlight the importance of the Neural Tangent Kernel variation for Continual Learning with OGD.
Code (1)
Tasks
Continual LearningTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ONG: Orthogonal Natural Gradient Descent
Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead …
Continual LearningRotated MNISTOn the Theory of Continual Learning with Gradient Descent for Neural Networks
Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study …
Continual LearningFisher-Orthogonal Projected Natural Gradient Descent for Continual Learning
Continual learning aims to enable neural networks to acquire new knowledge on sequential tasks. However, the key challenge in such settings is to learn new tasks without catastrophically forgetting previously learned tas…
Continual LearningMeta Mirror Descent: Optimiser Learning for Fast Convergence
Optimisers are an essential component for training machine learning models, and their design influences learning speed and generalisation. Several studies have attempted to learn more effective gradient-descent optimiser…
Meta-LearningDebugging using Orthogonal Gradient Descent
In this report we consider the following problem: Given a trained model that is partially faulty, can we correct its behaviour without having to train the model from scratch? In other words, can we ``debug" neural networ…
Continual Learning